Skills/Glama/mcp-legifrance

mcp-legifrance@r1

CAUTION· install only

Publisher claims: "Enables read-only querying of official French law — laws, codes, case law, CNIL deliberations and collective agreements — through the Légifrance PISTE API, returning source text with citations and links. It also resolves and verifies legal citations, compares article versions, and searches across multiple legal collections." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher muchiny · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso gouv.fr, evil.example, crates.io, rust-lang.org, app.test, proxy.example — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is mcp-legifrance@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionxtask/src/lock_descriptors.rs:885 · File type combined with upload action — agent may exfiltrate local data files"packaging/mcpb/manifest.json: input/output error",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathscrates/lf-adapter-dila/src/path.rs:440 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"legi/../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathscrates/lf-app/src/config.rs:2129 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("FR_ELI_ENV", "production")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Excessive HTML entities detectedcrates/lf-domain/src/text/html.rs:1039 · Excessive HTML entities detected — may be obfuscating content"&#0;&#x0;&#xD800;&#57343;&#x110000;&#1114112;&#+65;&#x+41;&#x;&#X;&#;&#1a;&#xg;";Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathscrates/lf-app/src/logging.rs:304 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("RUST_LOG", "trace")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathscrates/lf-adapter-dila/src/path.rs:463 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert_eq!(doc_for_key("../etc/passwd"), None);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionxtask/src/lock_descriptors.rs:918 · File type combined with upload action — agent may exfiltrate local data files"tests/tools.lock.json: input/output error"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathscrates/lf-app/src/config.rs:2130 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("FR_ELI_CACHE_DIR", " ")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandcrates/lf-app/src/shutdown.rs:115 · Process kill command — agent can terminate processesassert!(status.success(), "kill -{signal} a échoué");Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
URL with embedded credentialscrates/lf-app/src/config.rs:1614 · URL with embedded credentials — may be phishing or credential leaking"http://uinfo-name:[email protected]/x",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
URL with embedded credentialscrates/lf-app/src/config.rs:1612 · URL with embedded credentials — may be phishing or credential leaking"https://uinfo-name:[email protected]/x",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathscrates/lf-app/src/config.rs:2127 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env(CLIENT_ID, CHILD_MARKER)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Excessive HTML entities detectedcrates/lf-domain/src/text/html.rs:1035 · Excessive HTML entities detected — may be obfuscating contentassert_eq!(decode_entities("&#233;&#xE9;&#XE9;&#x0e9;&#00233;"), "ééééé");Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionxtask/src/lock_descriptors.rs:911 · File type combined with upload action — agent may exfiltrate local data filesformat!("packaging/mcpb/manifest.json: input/output error\n{UPDATE_HINT}")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathscrates/lf-app/src/config.rs:2128 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env(CLIENT_SECRET, " child-secret ")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionxtask/src/lock_descriptors.rs:887 · File type combined with upload action — agent may exfiltrate local data files(LockMode::Update, LOCK_PATH, false, "tests/tools.lock.json: input/output error"),Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathscrates/lf-app/src/config.rs:684 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsspikes/tls-provider/src/main.rs:327 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("TLS_PROBE_CHILD", "1")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionxtask/src/lock_descriptors.rs:880 · File type combined with upload action — agent may exfiltrate local data files(LockMode::Check, LOCK_PATH, false, "tests/tools.lock.json: input/output error"),Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandcrates/lf-app/src/shutdown.rs:112 · Process kill command — agent can terminate processes.args(["-c", &format!("kill -{signal} {}", std::process::id())])Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathscrates/lf-app/src/clock.rs:126 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("TZ", tz)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈37 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim muchiny: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. Excessive HTML entities detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim muchinyPropose a patch to the maintainer